Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
Wiki Rasa
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Iterations
Wiki
Requirements
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Locked files
Build
Pipelines
Jobs
Pipeline schedules
Test cases
Artifacts
Deploy
Releases
Package Registry
Model registry
Operate
Environments
Terraform modules
Monitor
Incidents
Service Desk
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Code review analytics
Issue analytics
Insights
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
tm-chatbot
Wiki Rasa
Commits
6f4a5bd9
Commit
6f4a5bd9
authored
6 years ago
by
Lucas Schons
Browse files
Options
Downloads
Patches
Plain Diff
Fix spelling errors
parent
350b2dd6
No related branches found
No related tags found
1 merge request
!71
Documentation: Final Report
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
docs/final-report/report.tex
+39
-36
39 additions, 36 deletions
docs/final-report/report.tex
with
39 additions
and
36 deletions
docs/final-report/report.tex
+
39
−
36
View file @
6f4a5bd9
...
@@ -23,36 +23,36 @@
...
@@ -23,36 +23,36 @@
% To be edited - my (Lukas) suggestion so far
% To be edited - my (Lukas) suggestion so far
\section
{
Project Description
}
\section
{
Project Description
}
\subsection
{
Convers
t
aional AI and Training
}
\subsection
{
Conversa
t
ional AI and Training
}
Conversational AI describes computer systems that users can interact with by having a
Conversational AI describes computer systems that users can interact with by having a
conversation. One important goal is to make the conversation seem as natural as possible.
conversation. One important goal is to make the conversation seem as natural as possible.
Ideally, an interacting user should assume to be interacting with another human
beeing
. This
Ideally, an interacting user should assume to be interacting with another human. This
can make communication with a computer become very pleasant and easy for human
ing beeing
s as
can make communication with a computer become very pleasant and easy for humans as
they are simply using the
language the always us
e. Besides there is no need for menu
they are simply using the
ir natural languag
e. Besides there is no need for menu
interaction with the system and thus no learning curve
required
.
interaction with the system and thus no learning curve.
% TODO add example use case (website information)
% TODO add example use case (website information)
% TODO add more benefits (24/7 availability)
% TODO add more benefits (24/7 availability)
\\
Conversational AI can be used in Voice Assistants that communicate through spoken words or
\\
Conversational AI can be used in Voice Assistants that communicate through spoken words or
through chatbots that imitate a human b
eeing one is chatting with by
text messages.
through chatbots that imitate a human b
y sending
text messages.
\subsection
{
Rasa Framwork
}
\subsection
{
Rasa Fram
e
work
}
Rasa is a collection of
framework
s for conversational AI software. The Rasa Stack contains two
Rasa is a collection of
tool
s for conversational AI software. The Rasa Stack contains two
open source libraries called Rasa NLU and Rasa Core that can be used to create contextual
open source libraries called Rasa NLU and Rasa Core that can be used to create contextual
chatbots. Rasa NLU is a library for natural language understanding with intent classification
chatbots. Rasa NLU is a library for natural language understanding with intent classification
and entity extraction Rasa Core is a
C
hatbot framework with machine learning based dialogue
and entity extraction Rasa Core is a
c
hatbot framework with machine learning based dialogue
management. Both can be uses independently but rasa recommends using both.
management. Both can be uses independently but rasa recommends using both.
% TODO add description of how a rasa bot must be trained to achieve results
% TODO add description of how a rasa bot must be trained to achieve results
\subsection
{
Research Question
}
\subsection
{
Research Question
}
The objective of this project is to find out, wether chatbots can be trained with natural
The objective of this project is to find out, wether chatbots can be trained with natural
language texts
\textit
{
automatically
}
. There are two inital research questions: Given that
language texts
\textit
{
automatically
}
. There are two init
i
al research questions: Given that
chatbots need to be trained with knowledge, called facts
.
chatbots need to be trained with knowledge, called facts
:
\begin{itemize}
\begin{itemize}
\item
C
an these facts be extracted from natural language text?
\item
c
an these facts be extracted from natural language text?
\item
C
an this be done automa
i
tcally?
\item
c
an this be done automat
i
cally?
\end{itemize}
\end{itemize}
\section
{
Solution
Approach
}
\section
{
Approach
}
\subsection
{
Project Goals
}
\subsection
{
Project Goals
}
\subsection
{
Rasa Setup and Intents
}
\subsection
{
Rasa Setup and Intents
}
\subsection
{
Scrapping of Source Texts
}
\subsection
{
Scrapping of Source Texts
}
...
@@ -61,11 +61,11 @@
...
@@ -61,11 +61,11 @@
\section
{
Software Architecture
}
\section
{
Software Architecture
}
\subsection
{
Rasa Chatbot
}
\subsection
{
Rasa Chatbot
}
The
Rasa C
hatbot built for this project uses both Rasa Stack components -
\textit
{
Rasa Core
}
The
c
hatbot built for this project uses both Rasa Stack components -
\textit
{
Rasa Core
}
and
\textit
{
Rasa NLU
}
. Configuration has been organi
s
ed in reference to examples from the Rasa
and
\textit
{
Rasa NLU
}
. Configuration has been organi
z
ed in reference to examples from the Rasa
github repository.
\\
Rasa NLU has been trained with example questions in
M
arkdown format that
github repository.
\\
Rasa NLU has been trained with example questions in
m
arkdown format that
contain highlighted enities. This ensures that the bot to understand intents and
extract the
contain highlighted en
t
ities. This ensures that the bot
is able
to understand intents and
entities inside the sentences. One example can be seen in listing
\ref
{
nlu
_
example
}
.
\\
extract the
entities inside the sentences. One example can be seen in listing
\ref
{
nlu
_
example
}
.
\\
\lstinputlisting
[label={nlu_example}, caption={NLU example}]
{
nlu
_
example.md
}
\lstinputlisting
[label={nlu_example}, caption={NLU example}]
{
nlu
_
example.md
}
...
@@ -74,7 +74,7 @@
...
@@ -74,7 +74,7 @@
contains all actions, entities, slots, intents, and templates the bot deals with.
\textit
contains all actions, entities, slots, intents, and templates the bot deals with.
\textit
{
Templates
}
means template strings for bot utterances.
\textit
{
Slots
}
are variables that can
{
Templates
}
means template strings for bot utterances.
\textit
{
Slots
}
are variables that can
hold different values. The bot proposed in this project uses a slot to store the name of a
hold different values. The bot proposed in this project uses a slot to store the name of a
recognized physicist entity
for instance
. According to the Rasa website
recognized physicist entity. According to the Rasa website
\footnote
{
\url
{
https://rasa.com/docs/get
_
started
_
step2/
}}
\footnote
{
\url
{
https://rasa.com/docs/get
_
started
_
step2/
}}
, the domain is
\textit
{
the universe the bot is living in
}
.
\\
, the domain is
\textit
{
the universe the bot is living in
}
.
\\
...
@@ -90,22 +90,25 @@
...
@@ -90,22 +90,25 @@
conversation ability available.
conversation ability available.
\begin{center}
\begin{center}
\begin{tabular}
{
| c | l | l |
}
\begin{table}
\hline
\begin{tabular}
{
| c | l | l |
}
No
&
Intent
&
Example
\\
\hline
\hline
1
&
birthdate
&
When was Albert Einstein born
\\
\hline
No
&
Intent
&
Example
\\
\hline
2
&
nationality
&
Where was Albert Einstein born
\\
\hline
1
&
birthdate
&
When was Albert Einstein born
\\
\hline
3
&
day of death
&
When did Albert Einstein die
\\
\hline
2
&
nationality
&
Where was Albert Einstein born
\\
\hline
4
&
place of death
&
Where did Albert Einstein die
\\
\hline
3
&
day of death
&
When did Albert Einstein die
\\
\hline
5
&
is alive
&
Is Albert Einstein still alive
\\
\hline
4
&
place of death
&
Where did Albert Einstein die
\\
\hline
6
&
spouse
&
Who was Albert Einstein married to
\\
\hline
5
&
is alive
&
Is Albert Einstein still alive
\\
\hline
7
&
primary education
&
Where did Albert Einstein go to school
\\
\hline
6
&
spouse
&
Who was Albert Einstein married to
\\
\hline
8
&
university
&
Which university did Albert Einstein attend
\\
\hline
7
&
primary education
&
Where did Albert Einstein go to school
\\
\hline
9
&
area of research
&
What was Albert Einstein area of research
\\
\hline
8
&
university
&
Which university did Albert Einstein attend
\\
\hline
10
&
workplace
&
Where did Albert Einstein work
\\
\hline
9
&
area of research
&
What was Albert Einstein area of research
\\
\hline
11
&
awards
&
What awards did Albert Einstein win
\\
\hline
10
&
workplace
&
Where did Albert Einstein work
\\
\hline
\end{tabular}
11
&
awards
&
What awards did Albert Einstein win
\\
\hline
\label
{
table:intent
_
table
}
\end{tabular}
\caption
{
Intents that are recognized by the bot
}
\label
{
table:intent
_
table
}
\end{table}
\end{center}
\end{center}
\subsection
{
R Package 'wikiproc'
}
\subsection
{
R Package 'wikiproc'
}
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment